Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    sky

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     validity
    -0.07
     condemnation
    -0.07
     hãy
    -0.07
     wavelength
    -0.07
     Patron
    -0.06
    穴
    -0.06
     �
    -0.06
    train
    -0.06
     commanded
    -0.06
    -column
    -0.06
    POSITIVE LOGITS
     sky
    0.08
     skies
    0.08
    �
    0.06
     yyn
    0.06
     «
    0.06
    .refs
    0.06
    bufio
    0.06
     fict
    0.06
    kyt
    0.06
    (sl
    0.06
    Act Density 0.011%

    No Known Activations